Development and validation of a nomogram to predict the risk of renal replacement therapy among acute kidney injury patients in intensive care unit

Abstract

Background: There are no universally accepted indications to initiate renal replacement therapy (RRT) among patients with acute kidney injury (AKI). This study aimed to develop a nomogram to predict the risk of RRT among AKI patients in intensive care unit (ICU).

Methods: In this retrospective cohort study, we extracted AKI patients from Medical Information Mart for Intensive Care III (MIMIC-III) database. Patients were randomly divided into a training cohort (70%) and a validation cohort (30%). Multivariable logistic regression based on Akaike information criterion was used to establish the nomogram. The discrimination and calibration of the nomogram were evaluated by Harrell's concordance index (C-index) and Hosmer-Lemeshow (HL) test. Decision curve analysis (DCA) was performed to evaluate clinical application.

Results: A total of 7413 critically ill patients with AKI were finally enrolled. 514 (6.9%) patients received RRT after ICU admission. 5194 (70%) patients were in the training cohort and 2219 (30%) patients were in the validation cohort. Nine variables, namely, age, hemoglobin, creatinine, blood urea nitrogen and lactate at AKI detection, comorbidity of congestive heart failure, AKI stage, and vasopressor use were included in the nomogram. The predictive model demonstrated satisfying discrimination and calibration with C-index of 0.938 (95% CI, 0.927-0.949; HL test, P = 0.430) in training set and 0.935 (95% CI, 0.919-0.951; HL test, P = 0.392) in validation set. DCA showed a positive net benefit of our nomogram.

Conclusion: The nomogram developed in this study was highly accurate for RRT prediction with potential application value.

Keywords: Acute kidney injury; Intensive care unit; MIMIC-III database; Nomogram; Renal replacement therapy.

Fig. 1

Flowchart of the included patients. KDIGO Kidney Disease: Improving Global Outcomes, MIMIC Medical Information Mart of Intensive Care, RRT renal replacement therapy

Fig. 2

The nomogram prediction score of RRT among AKI patients in ICU. When using it, drawing a vertical line from each variable to the point axis for the score, then the points for all the parameters were added; finally, a line from the total point axis was drawn to correspond the probability of RRT at the bottom. AKI acute kidney injury, BUN blood urea nitrogen, RRT renal replacement therapy, sCr serum creatinine, SOFA Sequential Organ Failure Assessment

Fig. 3

The receiver-operating characteristic (ROC) curves of the nomogram in the training cohort and validation cohort

Fig. 4

Calibration curve analysis in the training (A) and validation (B) cohorts. The horizontal axis represents the nomogram-predicted probability of RRT, and the vertical axis represents the actual observed probability of RRT. RRT renal replacement therapy

Fig. 5

Decision curve analysis of the nomogram, Scr, and BUN for the risk of RRT in the training cohort (A) and validation cohort (B). X-axis indicates the threshold probability for RRT and Y-axis indicates the net benefit. The gray line represents the assumption that all patients are treated with RRT. The thin black link represents the assumption that no patients are treated with RRT. The net benefit was calculated by subtracting the proportion of all patients who are false positive from the proportion who are true positive, weighting by the relative harm of forgoing treatment compared with the negative consequences of an unnecessary treatment. Here, the relative harm was calculated by ($\frac{P\mathrm{t}}{1-P\mathrm{t}}$). BUN blood urea nitrogen, P_t threshold probability, RRT renal replacement therapy, sCr serum creatinine